Abstract

Papers from the conference on AI Risk (published in JETAI), supplemented by additional work. --- If the intelligence of artificial systems were to surpass that of humans, humanity would face significant risks. The time has come to consider these issues, and this consideration must include progress in artificial intelligence (AI) as much as insights from AI theory. -- Featuring contributions from leading experts and thinkers in artificial intelligence, Risks of Artificial Intelligence is the first volume of collected chapters dedicated to examining the risks of AI. The book evaluates predictions of the future of AI, proposes ways to ensure that AI systems will be beneficial to humans, and then critically evaluates such proposals.1Vincent C. Müller, Editorial: Risks of Artificial Intelligence -2Steve Omohundro, Autonomous Technology and the Greater Human Good -3Stuart Armstrong, Kaj Sotala and Sean O’Heigeartaigh, The Errors, Insights and Lessons of Famous AI Predictions - and What they Mean for the Future -4Ted Goertzel, The Path to More General Artificial Intelligence -5Miles Brundage, Limitations and Risks of Machine Ethics -6Roman Yampolskiy, Utility Function Security in Artificially Intelligent Agents -7Ben Goertzel, GOLEM: Toward an AGI Meta-Architecture Enabling Both Goal Preservation and Radical Self-Improvement -8Alexey Potapov and Sergey Rodionov, Universal Empathy and Ethical Bias for Artificial General Intelligence -9András Kornai, Bounding the Impact of AGI -10Anders Sandberg, Ethics and Impact of Brain Emulations11Daniel Dewey, Long-Term Strategies for Ending Existential Risk from Fast Takeoff -12Mark Bishop, The Singularity, or How I Learned to Stop Worrying and Love AI -